Wan 2.1 I2V 14B 480P StepDistill CfgDistill Lightx2v
Wan2.1-I2V-14B-480P-StepDistill-CfgDistill-Lightx2v is an advanced image-to-video generation model built upon the Wan2.1-I2V-14B-480P foundation. This approach allows the model to generate videos with significantly...
Fuente del modelo
- Tipo
- Other
- Tamaño del archivo
- 21,6 MB–6,27 GB
- Modelo base
- Wan-AI/Wan2.1-I2V-14B-480P
- Versión
- vmain
- Actualizado
- 28 sept 2026
- Descargas
- 0
- Tareas
- Imagen a vídeo
- Fuente
- Hugging Face
Extracto de la fuente
Wan2.1-I2V-14B-480P-StepDistill-CfgDistill-Lightx2v is an advanced image-to-video generation model built upon the Wan2.1-I2V-14B-480P foundation. This approach allows the model to generate videos with significantly...
Fuentes
1 fuente
Fuentes
1 fuenteVerificado 28 sept
Artefactos del modelo
64 artefactos
Artefactos del modelo
64 artefactosdistill_fp8/block_0.safetensors
safetensors · 386 MB · SHA-256 8a13c9ed21e3…f512 · Hugging Face
Descargardistill_fp8/block_1.safetensors
safetensors · 386 MB · SHA-256 e36e70d8a4f0…22c7 · Hugging Face
Descargardistill_fp8/block_10.safetensors
safetensors · 386 MB · SHA-256 8c32b197849d…9d93 · Hugging Face
Descargardistill_fp8/block_11.safetensors
safetensors · 386 MB · SHA-256 1eb9a4430f41…8829 · Hugging Face
Descargardistill_fp8/block_12.safetensors
safetensors · 386 MB · SHA-256 37d76f0e2b55…4ff3 · Hugging Face
Descargardistill_fp8/block_13.safetensors
safetensors · 386 MB · SHA-256 0e658c630e47…a3e4 · Hugging Face
Descargardistill_fp8/block_14.safetensors
safetensors · 386 MB · SHA-256 d607c83c42aa…7571 · Hugging Face
Descargardistill_fp8/block_15.safetensors
safetensors · 386 MB · SHA-256 039d4199341d…ff27 · Hugging Face
Descargardistill_fp8/block_16.safetensors
safetensors · 386 MB · SHA-256 5c9b7ef49052…8d21 · Hugging Face
Descargardistill_fp8/block_17.safetensors
safetensors · 386 MB · SHA-256 13253e4faa52…2bdf · Hugging Face
Descargardistill_fp8/block_18.safetensors
safetensors · 386 MB · SHA-256 58213199765d…7e24 · Hugging Face
Descargardistill_fp8/block_19.safetensors
safetensors · 386 MB · SHA-256 05003c252069…0598 · Hugging Face
Descargardistill_fp8/block_2.safetensors
safetensors · 386 MB · SHA-256 77c1686dd705…0df9 · Hugging Face
Descargardistill_fp8/block_20.safetensors
safetensors · 386 MB · SHA-256 c351d87091e1…036b · Hugging Face
Descargardistill_fp8/block_21.safetensors
safetensors · 386 MB · SHA-256 a312f43266e9…80ac · Hugging Face
Descargardistill_fp8/block_22.safetensors
safetensors · 386 MB · SHA-256 8a761cc970f5…bec9 · Hugging Face
Descargardistill_fp8/block_23.safetensors
safetensors · 386 MB · SHA-256 a0b204b49f3b…3016 · Hugging Face
Descargardistill_fp8/block_24.safetensors
safetensors · 386 MB · SHA-256 4de844af9c11…43c7 · Hugging Face
Descargardistill_fp8/block_25.safetensors
safetensors · 386 MB · SHA-256 18337262ab68…ad8f · Hugging Face
Descargardistill_fp8/block_26.safetensors
safetensors · 386 MB · SHA-256 89f3b0b1edbe…c1ba · Hugging Face
Descargardistill_fp8/block_27.safetensors
safetensors · 386 MB · SHA-256 3084873e7aa3…c087 · Hugging Face
Descargardistill_fp8/block_28.safetensors
safetensors · 386 MB · SHA-256 b8a502c11baf…b836 · Hugging Face
Descargardistill_fp8/block_29.safetensors
safetensors · 386 MB · SHA-256 d0d461ddef6a…a6aa · Hugging Face
Descargardistill_fp8/block_3.safetensors
safetensors · 386 MB · SHA-256 c6458712a21c…a013 · Hugging Face
Descargardistill_fp8/block_30.safetensors
safetensors · 386 MB · SHA-256 d038db75d439…516c · Hugging Face
Descargardistill_fp8/block_31.safetensors
safetensors · 386 MB · SHA-256 ab98d2c3de31…533c · Hugging Face
Descargardistill_fp8/block_32.safetensors
safetensors · 386 MB · SHA-256 575b91e17bd0…e88c · Hugging Face
Descargardistill_fp8/block_33.safetensors
safetensors · 386 MB · SHA-256 2536f63d7939…a726 · Hugging Face
Descargardistill_fp8/block_34.safetensors
safetensors · 386 MB · SHA-256 c0d32e9adbfd…8ace · Hugging Face
Descargardistill_fp8/block_35.safetensors
safetensors · 386 MB · SHA-256 59b95887b85b…7309 · Hugging Face
Descargardistill_fp8/block_36.safetensors
safetensors · 386 MB · SHA-256 6496e46ed791…c7e2 · Hugging Face
Descargardistill_fp8/block_37.safetensors
safetensors · 386 MB · SHA-256 b0e08d56b8cb…c1c1 · Hugging Face
Descargardistill_fp8/block_38.safetensors
safetensors · 386 MB · SHA-256 fdeebb3c7c9d…1d46 · Hugging Face
Descargardistill_fp8/block_39.safetensors
safetensors · 386 MB · SHA-256 01e5efb7f9eb…477a · Hugging Face
Descargardistill_fp8/block_4.safetensors
safetensors · 386 MB · SHA-256 73a31967f573…fc63 · Hugging Face
Descargardistill_fp8/block_5.safetensors
safetensors · 386 MB · SHA-256 ef09b420a16b…84c1 · Hugging Face
Descargardistill_fp8/block_6.safetensors
safetensors · 386 MB · SHA-256 af5bd16384da…7ddb · Hugging Face
Descargardistill_fp8/block_7.safetensors
safetensors · 386 MB · SHA-256 758e1ba74a30…ff92 · Hugging Face
Descargardistill_fp8/block_8.safetensors
safetensors · 386 MB · SHA-256 a0eed8055bbb…d6be · Hugging Face
Descargardistill_fp8/block_9.safetensors
safetensors · 386 MB · SHA-256 eaf8fd7fe69c…47b6 · Hugging Face
Descargardistill_fp8/models_t5_umt5-xxl-enc-fp8.pth
pth · 6,27 GB · SHA-256 546b3b1c73d0…87f7 · Hugging Face
Descargardistill_fp8/non_block.safetensors
safetensors · 921 MB · SHA-256 1610ac0ed513…077d · Hugging Face
Descargardistill_int8/block_0.safetensors
safetensors · 386 MB · SHA-256 51e003dfa05a…a72d · Hugging Face
Descargardistill_int8/block_1.safetensors
safetensors · 386 MB · SHA-256 0d9522780b4d…72ec · Hugging Face
Descargardistill_int8/block_10.safetensors
safetensors · 386 MB · SHA-256 073d0bf5e63e…6795 · Hugging Face
Descargardistill_int8/block_11.safetensors
safetensors · 386 MB · SHA-256 b3f2d55371c0…abd0 · Hugging Face
Descargardistill_int8/block_12.safetensors
safetensors · 386 MB · SHA-256 c578677daf46…2bab · Hugging Face
Descargardistill_int8/block_13.safetensors
safetensors · 386 MB · SHA-256 8362be2dcfe6…b0c4 · Hugging Face
Descargardistill_int8/block_14.safetensors
safetensors · 386 MB · SHA-256 723e4ba04052…833b · Hugging Face
Descargardistill_int8/block_15.safetensors
safetensors · 386 MB · SHA-256 c695defa122d…2182 · Hugging Face
Descargardistill_int8/block_16.safetensors
safetensors · 386 MB · SHA-256 de4a63a4716f…25e6 · Hugging Face
Descargardistill_int8/block_17.safetensors
safetensors · 386 MB · SHA-256 23b34cbaa814…be1d · Hugging Face
Descargardistill_int8/block_18.safetensors
safetensors · 386 MB · SHA-256 f10ba7f44c07…e4b7 · Hugging Face
Descargardistill_int8/block_19.safetensors
safetensors · 386 MB · SHA-256 29728ced9f59…a262 · Hugging Face
Descargardistill_int8/block_2.safetensors
safetensors · 386 MB · SHA-256 2b8fce52f3a7…674a · Hugging Face
Descargardistill_int8/block_20.safetensors
safetensors · 386 MB · SHA-256 8c6db318ac07…d96c · Hugging Face
Descargardistill_int8/block_21.safetensors
safetensors · 386 MB · SHA-256 fe28d4d0bac0…69df · Hugging Face
Descargardistill_int8/block_22.safetensors
safetensors · 386 MB · SHA-256 8b3e20e8a919…40e3 · Hugging Face
Descargardistill_int8/block_23.safetensors
safetensors · 386 MB · SHA-256 9d3d61414a8d…7694 · Hugging Face
Descargardistill_int8/block_24.safetensors
safetensors · 386 MB · SHA-256 953f4ddd731a…82bc · Hugging Face
Descargardistill_int8/block_25.safetensors
safetensors · 386 MB · SHA-256 9b77e596ffc9…0262 · Hugging Face
DescargarExtractos de fuentes
2 extractos
Extractos de fuentes
2 extractos--- license: apache-2.0 language: - en - zh pipeline_tag: image-to-video tags: - video generation - diffusion-single-file - comfyui - distillation - LoRA library_name: diffusers inference: parameters: num_inference_steps: 4 base_model: - Wan-AI/Wan2.1-I2V-14B-480P --- # Wan2.1-I2V-14B-480P-StepDistill-CfgDistill-Lightx2v <p align="center"> <img src="assets/img_lightx2v.png" width=75%/> <p> ## Overview Wan2.1-I2V-14B-480P-StepDistill-CfgDistill-Lightx2v is an advanced image-to-video generation model built upon the Wan2.1-I2V-14B-480P foundation. This approach allows the model to generate videos with significantly fewer inference steps (4 steps) and without classifier-free guidance, substantially reducing video generation time while maintaining high quality outputs. In this version, we added the following features: 1. Trained with higher quality datasets for extended iterations. 2. New fp8 and int8 quantized distillation models have been added, which enable fast inference using lightx2v on RTX 4060. ## Training Our training code is modified based on the [Self-Forcing](https://github.com/guandeh17/Self-Forcing) repository. We extended support for the Wan2.1-14B-I2V-480P model and performed a 4-step bidirectional distillation process. The modified code is available at [Self-Forcing-Plus](https://github.com/GoatWu/Self-Forcing-Plus). ## Inference Our inference framework utilizes [lightx2v](https://github.com/ModelTC/lightx2v), a highly efficient inference engine that supports multiple models. This framework significantly accelerates the video generation process while maintaining high quality output. ```bash bash scripts/wan/run_wan_i2v_distill_4step_cfg.sh ``` or using the lora version: ```bash bash scripts/wan/run_wan_i2v_distill_4step_cfg_lora.sh ``` We recommend using the **LCM scheduler** with the following settings: - `shift=5.0` - `guidance_scale=1.0 (i.e., without CFG)` ## License Agreement The models in this repository are licensed under the Apache 2.0 License. We claim no rights over the your generate contents, granting you the freedom to use them while ensuring that your usage complies with the provisions of this license. You are fully accountable for your use of the models, which must not involve sharing any content that violates applicable laws, causes harm to individuals or groups, disseminates personal information intended fo...
Source context: 0 downloads · 135 likes · Pipeline image-to-video · Library diffusers · Repo lightx2v/Wan2.1-I2V-14B-480P-StepDistill-CfgDistill-Lightx2v
